arXiv subjects

Haydn Jones

Publications and source records attributed to Haydn Jones.

5 recordsLinked to original sources

arXiv2026

Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale

Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, and discard experimental context, obscuring nuances needed to assess data correctness and coverage. We show that PubMed itself can be autonomously and cost-effectively turned into structured datasets that are larger, more nuanced, and more accurate than the curated databases they replace. We present three coupled contributions: (1) an LLM-based entity-tagging pipeline, grounded in nine biomedical ontologies, that tags 4.5B entities across 19 categories in a 22.5M-paper, 2.5T-token PubMed corpus; (2) hybrid sparse-dense retrieval supporting entity-filtered semantic queries over the tagged corpus; and (3) Starling, a multi-agent deep research system that, given only a natural-language task description, designs precision- and recall-targeted retrieval filters, induces an extraction schema, and emits structured records with nuance-rich fields and supporting passages. Across six tasks -- blood-brain barrier permeability, oral bioavailability, acute toxicity (LD50), gene-disease associations, protein subcellular localization, and chemical reactions -- Starling produces ~6.3M records (91K-3M per task); several are, to our knowledge, the largest public datasets for their property. Frontier-model rejection of our extractions is 0.6-7.7% across tasks, far below error rates we measure on widely used curated counterparts (e.g., 16.5% on BBB_Martins, 7.3% on Bioavailability_Ma). Beyond scale and accuracy, the supporting passages carry nuance tabular databases discard -- e.g., oral bioavailability may depend on fed vs. fasted state. Together, the corpus, retrieval, and agent establish a foundation for AI-driven therapeutic design. Code and datasets: https://github.com/starling-labs/starling.

cs.LG↗

arXiv2025

Learned Offline Query Planning via Bayesian Optimization

Analytics database workloads often contain queries that are executed repeatedly. Existing optimization techniques generally prioritize keeping optimization cost low, normally well below the time it takes to execute a single instance of a query. If a given query is going to be executed thousands of times, could it be worth investing significantly more optimization time? In contrast to traditional online query optimizers, we propose an offline query optimizer that searches a wide variety of plans and incorporates query execution as a primitive. Our offline query optimizer combines variational auto-encoders with Bayesian optimization to find optimized plans for a given query. We compare our technique to the optimal plans possible with PostgreSQL and recent RL-based systems over several datasets, and show that our technique finds faster query plans.

cs.DB↗

arXiv2024

Bound Tightening using Rolling-Horizon Decomposition for Neural Network Verification

Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable their deployment in safety-critical applications. This paper introduces a new approach to neural network verification using a novel mixed-integer programming rolling-horizon decomposition method. The algorithm leverages the layered structure of neural networks, by employing optimization-based bound-tightening on smaller sub-graphs of the original network in a rolling-horizon fashion. This strategy strikes a balance between achieving tighter bounds and ensuring the tractability of the underlying mixed-integer programs. Extensive numerical experiments, conducted on instances from the VNN-COMP benchmark library, demonstrate that the proposed approach yields significantly improved bounds compared to existing effective bound propagation methods. Notably, the parallelizable nature of the proposed method proves effective in solving open verification problems. Our code is built and released as part of the open-source mathematical modeling tool Gravity (https://github.com/coin-or/Gravity), which is extended to support generic neural network models.

math.OC↗

arXiv2023

Large-Scale Gaussian Processes via Alternating Projection

Training and inference in Gaussian processes (GPs) require solving linear systems with $n\times n$ kernel matrices. To address the prohibitive $\mathcal{O}(n^3)$ time complexity, recent work has employed fast iterative methods, like conjugate gradients (CG). However, as datasets increase in magnitude, the kernel matrices become increasingly ill-conditioned and still require $\mathcal{O}(n^2)$ space without partitioning. Thus, while CG increases the size of datasets GPs can be trained on, modern datasets reach scales beyond its applicability. In this work, we propose an iterative method which only accesses subblocks of the kernel matrix, effectively enabling mini-batching. Our algorithm, based on alternating projection, has $\mathcal{O}(n)$ per-iteration time and space complexity, solving many of the practical challenges of scaling GPs to very large datasets. Theoretically, we prove the method enjoys linear convergence. Empirically, we demonstrate its fast convergence in practice and robustness to ill-conditioning. On large-scale benchmark datasets with up to four million data points, our approach accelerates GP training and inference by speed-up factors up to $27\times$ and $72 \times$, respectively, compared to CG.

cs.LG↗

arXiv2021

Magnetised quark nuggets in the atmosphere

A search for magnetised quark nuggets (MQN) is reported using acoustic signals from hydrophones placed in the Great Salt Lake (GSL) in the USA. No events satisfying the expected signature were seen. This observation allows limits to be set on the flux of MQNs penetrating the atmosphere and depositing energy in the GSL. The expected signature of the events was derived from pressure pulses caused by high-explosive cords between the lake surface and bottom at various locations in the GSL. The limits obtained from this search are compared with those obtained from previous searches and are compared to models for the formation of MQNs.

hep-ex↗